def main():
logger.info("Start Training Pipeline")
augmented = True
if augmented:
if not os.path.exists(
os.path.join(METADATA_DIR_AUGMENTED_PROCESSED, 'data.pkl')):
augment.main()
# Read Data
dataset = pd.read_pickle(
os.path.join(METADATA_DIR_AUGMENTED_PROCESSED, 'data.pkl'))
else:
# Generate MetaData if not generated yet
if not os.path.exists(os.path.join(METADATA_DIR_PROCESSED,
'data.pkl')):
generate.run()
dataset = pd.read_pickle(
os.path.join(METADATA_DIR_PROCESSED, 'data.pkl'))
logger.info(f"Number of samples: {len(dataset)}")
most_shape = get_most_shape(dataset)
train_data, test_data = train_test_split(dataset,
augmented=augmented,
split_ratio=0.65)
X_train, y_train = features_target_split(train_data)
X_test, y_test = features_target_split(test_data)
# Reshape for CNN input
X_train, X_test = reshape_feature_CNN(X_train), reshape_feature_CNN(X_test)
# Preserve y_test values
y_test_values = y_test.copy()
# One-Hot encoding for classes
y_train, y_test = one_hot_encode(y_train), one_hot_encode(y_test)
# Instance of CNN model
cnn = CNN(most_shape)
logger.info(str(cnn))
cnn.train(X_train, y_train, X_test, y_test)
cnn.evaluate(X_train, y_train, X_test, y_test)
predictions = cnn.model.predict_classes(X_test)
conf_matrix = confusion_matrix(y_test_values,
predictions,
labels=range(10))
logger.info('Confusion Matrix for classes {}:\n{}'.format(
CLASSES, conf_matrix))
cnn.save_model()
if not os.path.exists(os.path.join(PROCESSED_METADATA_DIR,
'data.pkl')):
run()
dataset = pd.read_pickle(
os.path.join(PROCESSED_METADATA_DIR, 'data.pkl'))
print(f"Number of samples: {len(dataset)}")
most_shape = get_most_shape(dataset)
train_data, test_data = train_test_split(dataset,
augmented=False,
split_ratio=0.65)
X_train, y_train = features_target_split(train_data)
X_test, y_test = features_target_split(test_data)
# Reshape for CNN input
X_train, X_test = reshape_feature_CNN(X_train), reshape_feature_CNN(X_test)
# Preserve y_test values
y_test_values = y_test.copy()
# One-Hot encoding for classes
y_train, y_test = one_hot_encode(y_train), one_hot_encode(y_test)
# Instance of CNN model
cnn = CNN(most_shape)
print(str(cnn))
cnn.train(X_train, y_train, X_test, y_test)
cnn.evaluate(X_train, y_train, X_test, y_test)
predictions = cnn.model.predict_classes(X_test)
conf_matrix = confusion_matrix(y_test_values,
predictions,
labels=range(10))
print('Confusion Matrix for classes {}:\n{}'.format(CLASSES, conf_matrix))
cnn.save_model()
# Normalize the data the training and val sets
train_df, val_df = AvgNormalization(df_train, df_val)
# Create windowed data sets and labels. Display summary.
w1 = WindowGenerator(input_width=24,
label_width=1,
shift=1,
train_df=train_df,
val_df=val_df,
label_columns=['Pressure'])
print(w1)
# Import models from source
MAX_EPOCHS = 20
val_performance = {}
# Testing CNN Model
history = compile_and_fit(CNN, w1, MAX_EPOCHS)
val_performance['CNN'] = CNN.evaluate(w1.val)
plot_loss(history, 'CNN_Model_Loss')
# Testing RNN Model
history = compile_and_fit(RNN, w1, MAX_EPOCHS)
val_performance['RNN'] = RNN.evaluate(w1.val)
plot_loss(history, 'RNN_Model_Loss')
# Performance Summary
for name, value in val_performance.items():
print(f'{name:12s}: {value[1]:0.4f}')